Facial landmark detection in real-time with correlation filtering

Viridiana Contreras; Víctor H. Díaz-Ramírez

doi:10.1117/12.2238098

Facial landmark detection in real-time with correlation filtering

Viridiana Contreras, Víctor H. Díaz-Ramírez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

An algorithm for facial landmark detection based on template matched filtering is presented. The algorithm is able to detect and estimate the position of a set of prespecified landmarks by employing a bank of linear filters. Each filter in the bank is trained to detect a single landmark that is located in a small region of the input face image. The filter bank is implemented in parallel on a graphics processing unit to perform facial landmark detection in real-time. Computer simulation results obtained with the proposed algorithm are presented and discussed in terms of detection rate, accuracy of landmark location estimation, and real-time efficiency.

Original language	English
Title of host publication	Applications of Digital Image Processing XXXIX
Editors	Andrew G. Tescher
Publisher	SPIE
ISBN (Electronic)	9781510603332
DOIs	https://doi.org/10.1117/12.2238098
State	Published - 2016
Externally published	Yes
Event	Applications of Digital Image Processing XXXIX - San Diego, United States Duration: 29 Aug 2016 → 1 Sep 2016

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	9971
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Applications of Digital Image Processing XXXIX
Country/Territory	United States
City	San Diego
Period	29/08/16 → 1/09/16

Keywords

Correlation filtering
Facial landmark detection
Graphics processing unit
Real-time image processing

Access to Document

10.1117/12.2238098

Cite this

@inproceedings{7ff813fe6a3540ed8a296495e62aaf84,

title = "Facial landmark detection in real-time with correlation filtering",

abstract = "An algorithm for facial landmark detection based on template matched filtering is presented. The algorithm is able to detect and estimate the position of a set of prespecified landmarks by employing a bank of linear filters. Each filter in the bank is trained to detect a single landmark that is located in a small region of the input face image. The filter bank is implemented in parallel on a graphics processing unit to perform facial landmark detection in real-time. Computer simulation results obtained with the proposed algorithm are presented and discussed in terms of detection rate, accuracy of landmark location estimation, and real-time efficiency.",

keywords = "Correlation filtering, Facial landmark detection, Graphics processing unit, Real-time image processing",

author = "Viridiana Contreras and D{\'i}az-Ram{\'i}rez, {V{\'i}ctor H.}",

note = "Publisher Copyright: {\textcopyright} 2016 SPIE.; Applications of Digital Image Processing XXXIX ; Conference date: 29-08-2016 Through 01-09-2016",

year = "2016",

doi = "10.1117/12.2238098",

language = "Ingl{\'e}s",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Tescher, {Andrew G.}",

booktitle = "Applications of Digital Image Processing XXXIX",

address = "Estados Unidos",

}

Contreras, V & Díaz-Ramírez, VH 2016, Facial landmark detection in real-time with correlation filtering. in AG Tescher (ed.), Applications of Digital Image Processing XXXIX., 997123, Proceedings of SPIE - The International Society for Optical Engineering, vol. 9971, SPIE, Applications of Digital Image Processing XXXIX, San Diego, United States, 29/08/16. https://doi.org/10.1117/12.2238098

Facial landmark detection in real-time with correlation filtering. / Contreras, Viridiana; Díaz-Ramírez, Víctor H.
Applications of Digital Image Processing XXXIX. ed. / Andrew G. Tescher. SPIE, 2016. 997123 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 9971).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Facial landmark detection in real-time with correlation filtering

AU - Contreras, Viridiana

AU - Díaz-Ramírez, Víctor H.

PY - 2016

Y1 - 2016

N2 - An algorithm for facial landmark detection based on template matched filtering is presented. The algorithm is able to detect and estimate the position of a set of prespecified landmarks by employing a bank of linear filters. Each filter in the bank is trained to detect a single landmark that is located in a small region of the input face image. The filter bank is implemented in parallel on a graphics processing unit to perform facial landmark detection in real-time. Computer simulation results obtained with the proposed algorithm are presented and discussed in terms of detection rate, accuracy of landmark location estimation, and real-time efficiency.

AB - An algorithm for facial landmark detection based on template matched filtering is presented. The algorithm is able to detect and estimate the position of a set of prespecified landmarks by employing a bank of linear filters. Each filter in the bank is trained to detect a single landmark that is located in a small region of the input face image. The filter bank is implemented in parallel on a graphics processing unit to perform facial landmark detection in real-time. Computer simulation results obtained with the proposed algorithm are presented and discussed in terms of detection rate, accuracy of landmark location estimation, and real-time efficiency.

KW - Correlation filtering

KW - Facial landmark detection

KW - Graphics processing unit

KW - Real-time image processing

UR - http://www.scopus.com/inward/record.url?scp=85006901803&partnerID=8YFLogxK

U2 - 10.1117/12.2238098

DO - 10.1117/12.2238098

M3 - Contribución a la conferencia

AN - SCOPUS:85006901803

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Applications of Digital Image Processing XXXIX

A2 - Tescher, Andrew G.

PB - SPIE

T2 - Applications of Digital Image Processing XXXIX

Y2 - 29 August 2016 through 1 September 2016

ER -

Facial landmark detection in real-time with correlation filtering

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this